Agent and capability manifests
Defined as an explicit contract so operators can review it before it runs.
Agents, MCP & capabilities · Concept
A packaging and distribution platform for installable AI agents, capabilities, skills, tools and reusable enterprise automation components.
AgentPlugin is built for Agent developers, software vendors, enterprise builders, capability publishers.
AgentPlugin replaces manual agent installation, proprietary plugin formats and custom integration packaging.
A packaging and distribution platform for installable AI agents, capabilities, skills, tools and reusable enterprise automation components.
Work stays inside an explicit scope: named sources, defined permissions, bounded execution, retained evidence.
Five contracts the product is specified around. Each one is a boundary as much as a feature.
Defined as an explicit contract so operators can review it before it runs.
Available through the product surface and the machine interfaces, with permission attached.
Available through the product surface and the machine interfaces, with permission attached.
Exposed as a scoped capability with its own evidence trail, not a hidden setting.
Exposed as a scoped capability with its own evidence trail, not a hidden setting.
The same three steps apply whether a person or an agent is driving.
Start from the boundary AgentPlugin is allowed to act inside: the workspace, the sources, the budget, the authority.
Expose the same capability through the interface a human uses and the interface an agent calls, with one permission model.
Every action leaves a record that can be inspected, replayed and challenged before the next one runs.
AgentPlugin is documented as a concept: requirements, interfaces and evidence expectations. It is not presented as a live service.